Youtube-Code-Repository icon indicating copy to clipboard operation
Youtube-Code-Repository copied to clipboard

Repository for most of the code from my YouTube channel

Results 48 Youtube-Code-Repository issues
Sort by recently updated
recently updated
newest added

Hi Phil, there is a small issue in the method **update_network_parameters(self)**, I think that should be: `self.q_target.set_weights(self.q_eval.get_weights())` instead of: `self.q_target.model.set_weights(self.q_eval.model.get_weights())` Thanks for your code and your videos! These are really...

My collection is looking better and better. Check out the: Volcano Dragon!![share_image_1707241047165.png](https://github.com/philtabor/Youtube-Code-Repository/assets/159102840/53c03916-3afe-4b74-85b5-2df7b361ded3)

Hi guys, I was trying Phil's code on my new server. The code he did is available [here](https://github.com/philtabor/Youtube-Code-Repository/blob/master/ReinforcementLearning/PolicyGradient/actor_critic/continuous_mountain_car_actor_critic.py) and [here](https://github.com/philtabor/Youtube-Code-Repository/blob/master/ReinforcementLearning/PolicyGradient/actor_critic/actor_critic_continuous.py). Since I didn't change the code (the only change is...

Good day! I have already watched the video and browsed through files. Im relatively new to DDPG DRL and I would like to know if I can use this to...

Hi! I have a few more questions about the code that I don't quite get. First, I was wondering what pybullet_envs is for. I installed the library but got errors...

(array([-0.02680779, 0.00466264, -0.02511859, -0.04842809], dtype=float32), {}) Traceback (most recent call last): File "main.py", line 31, in action, prob, val = agent.choose_action(observation) File "D:\AI\PPO\agent.py", line 41, in choose_action state = tf.convert_to_tensor([observation],dtype=tf.float32)...

I'm interested in switching out the [default keras NNs](https://github.com/philtabor/Youtube-Code-Repository/blob/1ef76059bf55f7df9ccc09fce0e0bfb7c13e89bd/ReinforcementLearning/PolicyGradient/PPO/tf2/networks.py) for catboost or other non NN models. Any guidance on how to accomplish it highly appreciated.

![image](https://user-images.githubusercontent.com/54039268/224358982-5245766d-e944-49ca-b05f-d54404291ce0.png) I got this issue when I run the a3c.py, I also found someone has the same error as me on this link https://github.com/facebookresearch/fairscale/issues/1083 I thought this because of the...